mistral-instruct-adv-robust-15-sft-lora

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.7347

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0003
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 16
• total_train_batch_size: 256
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
3.1318	0.12	1	2.8353
3.1318	1.12	2	2.6364
3.1318	2.12	3	2.4946
3.1318	3.12	4	2.5337
2.7387	4.12	5	2.3354
2.7387	5.12	6	2.2143
2.7387	6.12	7	2.1649
2.7387	7.12	8	2.1062
2.7387	8.12	9	2.0854
2.2698	9.12	10	2.0497
2.2698	10.12	11	1.9576
2.2698	11.12	12	1.8585
2.2698	12.12	13	1.7771
2.2698	13.12	14	1.7952
1.9483	14.12	15	1.7796

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0a0+32f93b1
• Datasets 2.14.6
• Tokenizers 0.14.1